© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162405
    Prev
    Next
    INDEX
    Explanations

    donations, funding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    人æŃ»äº¡
    -0.26
    å°ĸåı«
    -0.25
    ClickListener
    -0.24
    logan
    -0.24
    igers
    -0.24
    бел
    -0.24
     Redistribution
    -0.24
    лик
    -0.24
    IZES
    -0.23
    æĹĹèĪ°
    -0.23
    POSITIVE LOGITS
    dam
    0.29
    ve
    0.27
     facilities
    0.25
     covered
    0.25
    gu
    0.24
     provided
    0.24
    rade
    0.24
    veis
    0.24
    çªĿ
    0.24
    stüt
    0.24
    Activations Density 0.003%

    No Known Activations